Skip to contentSkip to filters

We use cookies for analytics.

Full-time position

Research Engineer / Research Scientist - Post Training, Personalization

OpenAI

Related content

About

Research post-training methods for models that adapt to users across interactions. Develop datasets and evaluations that measure personalization and use reinforcement learning and other post-training methods to improve how models integrate relevant user context.

Requirements

Strong engineering or ML research background, with the ability to design evaluations, run experiments and translate findings into model improvements. The role is based in San Francisco with three office days per week.

Topics

Source: OpenAI